EP3710990A4 - Méta-apprentissage pour apprentissage multitâche pour réseaux neuronaux - Google Patents
Méta-apprentissage pour apprentissage multitâche pour réseaux neuronaux Download PDFInfo
- Publication number
- EP3710990A4 EP3710990A4 EP18877988.8A EP18877988A EP3710990A4 EP 3710990 A4 EP3710990 A4 EP 3710990A4 EP 18877988 A EP18877988 A EP 18877988A EP 3710990 A4 EP3710990 A4 EP 3710990A4
- Authority
- EP
- European Patent Office
- Prior art keywords
- learning
- meta
- neural networks
- tasking
- tasking learning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/047—Probabilistic or stochastic networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/09—Supervised learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/0985—Hyperparameter optimisation; Meta-learning; Learning-to-learn
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Probability & Statistics with Applications (AREA)
- Image Analysis (AREA)
- Feedback Control In General (AREA)
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US201762586154P | 2017-11-14 | 2017-11-14 | |
| PCT/US2018/060158 WO2019099305A1 (fr) | 2017-11-14 | 2018-11-09 | Méta-apprentissage pour apprentissage multitâche pour réseaux neuronaux |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| EP3710990A1 EP3710990A1 (fr) | 2020-09-23 |
| EP3710990A4 true EP3710990A4 (fr) | 2021-10-27 |
Family
ID=66431300
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP18877988.8A Withdrawn EP3710990A4 (fr) | 2017-11-14 | 2018-11-09 | Méta-apprentissage pour apprentissage multitâche pour réseaux neuronaux |
Country Status (9)
| Country | Link |
|---|---|
| US (2) | US11048978B2 (fr) |
| EP (1) | EP3710990A4 (fr) |
| JP (1) | JP7213241B2 (fr) |
| KR (1) | KR102839893B1 (fr) |
| CN (1) | CN111328400B (fr) |
| AU (1) | AU2018368279A1 (fr) |
| CA (1) | CA3080005A1 (fr) |
| IL (1) | IL274424B2 (fr) |
| WO (1) | WO2019099305A1 (fr) |
Families Citing this family (107)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA3080005A1 (fr) * | 2017-11-14 | 2019-05-23 | Magic Leap, Inc. | Meta-apprentissage pour apprentissage multitache pour reseaux neuronaux |
| EP3502978A1 (fr) * | 2017-12-22 | 2019-06-26 | Siemens Healthcare GmbH | Système de méta-apprentissage |
| US10802489B1 (en) | 2017-12-29 | 2020-10-13 | Apex Artificial Intelligence Industries, Inc. | Apparatus and method for monitoring and controlling of a neural network using another neural network implemented on one or more solid-state chips |
| US11501076B2 (en) * | 2018-02-09 | 2022-11-15 | Salesforce.Com, Inc. | Multitask learning as question answering |
| US11354459B2 (en) * | 2018-05-08 | 2022-06-07 | Microsoft Technology Licensing, Llc | Computer vision and speech algorithm design service |
| US20210257067A1 (en) * | 2018-08-31 | 2021-08-19 | Nippon Telegraph And Telephone Corporation | State transition prediction device, and device, method, and program for learning predictive model |
| CN112789626B (zh) | 2018-09-27 | 2024-11-08 | 渊慧科技有限公司 | 可扩展和压缩的神经网络数据储存系统 |
| WO2020176112A1 (fr) * | 2019-02-26 | 2020-09-03 | Google Llc | Techniques d'apprentissage par renforcement permettant de sélectionner un réseau de politiques de logiciels et de commander de manière autonome un client logiciel correspondant d'après le réseau de politiques sélectionné |
| US11610414B1 (en) * | 2019-03-04 | 2023-03-21 | Apple Inc. | Temporal and geometric consistency in physical setting understanding |
| EP3938898A4 (fr) * | 2019-03-13 | 2023-03-29 | Cognizant Technology Solutions U.S. Corporation | Système et procédé permettant de mettre en oeuvre un reparamétrage universel modulaire pour un apprentissage multitâche profond à travers divers domaines |
| US11783195B2 (en) | 2019-03-27 | 2023-10-10 | Cognizant Technology Solutions U.S. Corporation | Process and system including an optimization engine with evolutionary surrogate-assisted prescriptions |
| CN110298330B (zh) * | 2019-07-05 | 2023-07-18 | 东北大学 | 一种输电线路巡检机器人单目检测与定位方法 |
| US12547759B2 (en) * | 2019-08-14 | 2026-02-10 | Google Llc | Privacy preserving machine learning model training |
| US11755884B2 (en) * | 2019-08-20 | 2023-09-12 | Micron Technology, Inc. | Distributed machine learning with privacy protection |
| CN110580500B (zh) * | 2019-08-20 | 2023-04-18 | 天津大学 | 一种面向人物交互的网络权重生成少样本图像分类方法 |
| US11636334B2 (en) | 2019-08-20 | 2023-04-25 | Micron Technology, Inc. | Machine learning with feature obfuscation |
| US11392796B2 (en) | 2019-08-20 | 2022-07-19 | Micron Technology, Inc. | Feature dictionary for bandwidth enhancement |
| CN110533184B (zh) * | 2019-08-31 | 2023-01-06 | 南京人工智能高等研究院有限公司 | 一种网络模型的训练方法及装置 |
| CN110598711B (zh) * | 2019-08-31 | 2022-12-16 | 华南理工大学 | 一种结合分类任务的目标分割方法 |
| US11551675B2 (en) | 2019-09-03 | 2023-01-10 | Samsung Electronics Co., Ltd. | Electronic device and method for controlling the electronic device thereof |
| CN110705756B (zh) * | 2019-09-07 | 2023-05-12 | 创新奇智(重庆)科技有限公司 | 一种基于输入凸神经网络的电力能耗优化控制方法 |
| CN110796260B (zh) * | 2019-09-11 | 2022-04-19 | 浙江大学 | 一种基于类扩张学习的神经网络模型优化方法 |
| US11640528B2 (en) * | 2019-10-22 | 2023-05-02 | Baidu Usa Llc | Method, electronic device and computer readable medium for information processing for accelerating neural network training |
| CN110852447B (zh) * | 2019-11-15 | 2023-11-07 | 腾讯云计算（北京）有限责任公司 | 元学习方法和装置、初始化方法、计算设备和存储介质 |
| CN110909885B (zh) * | 2019-11-19 | 2022-09-23 | 支付宝(杭州)信息技术有限公司 | 一种平衡多个任务的方法及系统 |
| US11366434B2 (en) | 2019-11-26 | 2022-06-21 | Apex Artificial Intelligence Industries, Inc. | Adaptive and interchangeable neural networks |
| US12081646B2 (en) | 2019-11-26 | 2024-09-03 | Apex Ai Industries, Llc | Adaptively controlling groups of automated machines |
| US10691133B1 (en) * | 2019-11-26 | 2020-06-23 | Apex Artificial Intelligence Industries, Inc. | Adaptive and interchangeable neural networks |
| US11367290B2 (en) | 2019-11-26 | 2022-06-21 | Apex Artificial Intelligence Industries, Inc. | Group of neural networks ensuring integrity |
| US10956807B1 (en) | 2019-11-26 | 2021-03-23 | Apex Artificial Intelligence Industries, Inc. | Adaptive and interchangeable neural networks utilizing predicting information |
| CN112734798B (zh) * | 2019-11-27 | 2023-11-07 | 上海联影智能医疗科技有限公司 | 神经网络的在线自适应系统和方法 |
| CN110929794B (zh) * | 2019-11-28 | 2022-12-13 | 哈尔滨工程大学 | 一种基于多任务学习的侧扫声呐图像分类方法 |
| US11348291B2 (en) * | 2019-11-29 | 2022-05-31 | Shanghai United Imaging Intelligence Co., Ltd. | System and method for reconstructing magnetic resonance images |
| CN111192248B (zh) * | 2019-12-30 | 2023-05-05 | 山东大学 | 一种用于核磁共振成像中的椎体定位、识别和分割的多任务关系学习方法 |
| CN111324695B (zh) * | 2020-02-06 | 2022-12-16 | 鼎富智能科技有限公司 | 一种多任务学习方法及装置 |
| CN111368998B (zh) * | 2020-03-04 | 2025-02-11 | 深圳前海微众银行股份有限公司 | 基于Spark集群的模型训练方法、装置、设备及存储介质 |
| CN113365072B (zh) * | 2020-03-06 | 2022-07-01 | 腾讯美国有限责任公司 | 特征图压缩方法、装置、计算设备以及存储介质 |
| CN113468924B (zh) * | 2020-03-31 | 2024-06-18 | 北京沃东天骏信息技术有限公司 | 关键点检测模型训练方法和装置、关键点检测方法和装置 |
| CN111476292B (zh) * | 2020-04-03 | 2021-02-19 | 北京全景德康医学影像诊断中心有限公司 | 医学图像分类处理人工智能的小样本元学习训练方法 |
| US12099934B2 (en) * | 2020-04-07 | 2024-09-24 | Cognizant Technology Solutions U.S. Corporation | Framework for interactive exploration, evaluation, and improvement of AI-generated solutions |
| KR20210150233A (ko) * | 2020-06-03 | 2021-12-10 | 삼성전자주식회사 | 이미지 처리 알고리즘의 최적화 방법 및 이를 구비한 전자 장치 |
| US11586919B2 (en) * | 2020-06-12 | 2023-02-21 | International Business Machines Corporation | Task-oriented machine learning and a configurable tool thereof on a computing environment |
| US11775841B2 (en) | 2020-06-15 | 2023-10-03 | Cognizant Technology Solutions U.S. Corporation | Process and system including explainable prescriptions through surrogate-assisted evolution |
| CN111797762B (zh) * | 2020-07-02 | 2026-02-17 | 北京灵汐科技有限公司 | 一种场景识别方法和系统 |
| US12424335B2 (en) | 2020-07-08 | 2025-09-23 | Cognizant Technology Solutions U.S. Corporation | AI based optimized decision making for epidemiological modeling |
| CN111860840B (zh) * | 2020-07-28 | 2023-10-17 | 上海联影医疗科技股份有限公司 | 深度学习模型训练方法、装置、计算机设备及存储介质 |
| CN111967594A (zh) * | 2020-08-06 | 2020-11-20 | 苏州浪潮智能科技有限公司 | 一种神经网络压缩方法、装置、设备及存储介质 |
| CN113743111B (zh) * | 2020-08-25 | 2024-06-04 | 国家计算机网络与信息安全管理中心 | 基于文本预训练和多任务学习的金融风险预测方法及装置 |
| KR102397079B1 (ko) * | 2020-09-07 | 2022-05-12 | 울산과학기술원 | 단일 뉴럴 네트워크를 이용한 로봇 파지 방법 및 이를 수행하는 장치 |
| EP3965020A1 (fr) * | 2020-09-07 | 2022-03-09 | Siemens Aktiengesellschaft | Modèle pour un détecteur d'anomalie continue rapide |
| CN112116002A (zh) * | 2020-09-18 | 2020-12-22 | 北京旋极信息技术股份有限公司 | 一种检测模型的确定方法、验证方法和装置 |
| CN112115265A (zh) * | 2020-09-25 | 2020-12-22 | 中国科学院计算技术研究所苏州智能计算产业技术研究院 | 文本分类中的小样本学习方法 |
| CN114248265B (zh) * | 2020-09-25 | 2023-07-07 | 广州中国科学院先进技术研究所 | 一种基于元模拟学习的多任务智能机器人学习方法及装置 |
| CN112180726A (zh) * | 2020-09-29 | 2021-01-05 | 北京航空航天大学 | 一种基于元学习的航天器相对运动轨迹规划方法 |
| CN112466281A (zh) * | 2020-10-13 | 2021-03-09 | 讯飞智元信息科技有限公司 | 有害音频识别解码方法及装置 |
| US12579464B1 (en) * | 2020-10-29 | 2026-03-17 | Amazon Technologies, Inc. | Meta-models for predicting machine learning model performance using features obtained via optimization |
| US11977602B2 (en) * | 2020-11-10 | 2024-05-07 | Nec Corporation | Domain generalized margin via meta-learning for deep face recognition |
| US11868439B2 (en) | 2020-11-13 | 2024-01-09 | Toyota Research Institute, Inc. | Mixed-batch training of a multi-task network |
| CN112560948B (zh) * | 2020-12-15 | 2024-04-26 | 中南大学 | 数据偏差下的眼底图分类方法及成像方法 |
| CN112561180B (zh) * | 2020-12-21 | 2022-05-17 | 深圳大学 | 基于元学习的短期风速预测方法、装置、计算机设备及存储介质 |
| CN116685963B (zh) * | 2020-12-23 | 2024-09-06 | 华为技术有限公司 | 用于预测性计算机建模的装置和方法 |
| CN112562069B (zh) * | 2020-12-24 | 2023-10-27 | 北京百度网讯科技有限公司 | 三维模型的构造方法、装置、设备和存储介质 |
| CN112766323A (zh) * | 2020-12-30 | 2021-05-07 | 清华大学 | 一种影像识别方法和装置 |
| KR102639179B1 (ko) * | 2020-12-31 | 2024-02-20 | 서울과학기술대학교 산학협력단 | 딥러닝 네트워크의 불확실도 판단방법 |
| CN112328646B (zh) * | 2021-01-04 | 2021-04-06 | 平安科技（深圳）有限公司 | 多任务课程推荐方法、装置、计算机设备及存储介质 |
| CN113780321A (zh) * | 2021-01-13 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | 图片审核方法、系统、电子设备及计算机可读介质 |
| CN114819042B (zh) * | 2021-01-19 | 2026-04-21 | 华为技术有限公司 | 一种参数优化方法及相关装置 |
| CN112785005B (zh) * | 2021-01-22 | 2023-02-03 | 中国平安人寿保险股份有限公司 | 多目标任务的辅助决策方法、装置、计算机设备及介质 |
| CN113159275A (zh) * | 2021-03-05 | 2021-07-23 | 深圳市商汤科技有限公司 | 网络训练方法、图像处理方法、装置、设备及存储介质 |
| US12086695B2 (en) * | 2021-03-18 | 2024-09-10 | Toyota Research Institute, Inc. | System and method for training a multi-task model |
| KR102833517B1 (ko) * | 2021-03-22 | 2025-07-15 | 재단법인대구경북과학기술원 | 메타 학습 기반 이미지 정합 모델 생성 방법 및 장치 |
| CN115131645A (zh) * | 2021-03-26 | 2022-09-30 | 佳能株式会社 | 神经网络的训练和应用方法、装置及存储介质 |
| CN113128432B (zh) * | 2021-04-25 | 2022-09-06 | 四川大学 | 基于演化计算的机器视觉多任务神经网络架构搜索方法 |
| WO2022261194A2 (fr) | 2021-06-08 | 2022-12-15 | Cognizant Technology Solutions U.S. Corporation | Système et procédé de génération de prescripteurs améliorés |
| CN113568735B (zh) * | 2021-06-17 | 2024-01-23 | 阿里巴巴新加坡控股有限公司 | 数据处理方法及系统 |
| CN113538349A (zh) * | 2021-06-29 | 2021-10-22 | 山东师范大学 | 基于模型无关元学习的小样本糖尿病视网膜病变分类系统 |
| CN113791882B (zh) * | 2021-08-25 | 2023-10-20 | 北京百度网讯科技有限公司 | 多任务的部署方法、装置、电子设备及存储介质 |
| CN113837379B (zh) * | 2021-09-14 | 2024-08-13 | 上海商汤智能科技有限公司 | 神经网络的训练方法及装置、计算机可读存储介质 |
| CN114185039B (zh) * | 2021-12-08 | 2025-09-23 | 中国人民解放军海军航空大学 | 雷达目标一维距离像智能识别方法 |
| KR102631937B1 (ko) * | 2021-12-22 | 2024-01-30 | 고려대학교 산학협력단 | 메타 학습을 통한 삼차원 사람 메쉬 복원 방법 및 장치 |
| CN114417497B (zh) * | 2021-12-23 | 2025-11-11 | 中国人民解放军军事科学院国防科技创新研究院 | 基于元学习的内嵌物理知识的神经网络初始化设计方法 |
| CN114387543B (zh) * | 2021-12-30 | 2025-05-09 | 网易有道信息技术（北京）有限公司 | 用于检测坐姿和学情状态的方法及其相关产品 |
| CN114358250B (zh) * | 2021-12-31 | 2025-08-15 | 腾讯科技（深圳）有限公司 | 数据处理方法、装置、计算机设备、介质及程序产品 |
| CN114037024A (zh) * | 2022-01-07 | 2022-02-11 | 心鉴智控(深圳)科技有限公司 | 一种基于多任务神经网络数据识别系统及方法 |
| TWI795173B (zh) * | 2022-01-17 | 2023-03-01 | 中華電信股份有限公司 | 多語言語音辨識系統、方法及電腦可讀媒介 |
| DE102022202030A1 (de) | 2022-02-28 | 2023-08-31 | Robert Bosch Gesellschaft mit beschränkter Haftung | Verfahren zum Trainieren eines bedingten neuronalen Prozesses zur Ermittlung einer Position eines Objektes aus Bilddaten |
| CN114818864B (zh) * | 2022-03-28 | 2025-08-08 | 深圳大学 | 一种基于小样本的手势识别方法 |
| US12346813B2 (en) * | 2022-07-28 | 2025-07-01 | Rakuten Group, Inc. | Online knowledge distillation for multi-task learning system, method, device, and program |
| US20240054336A1 (en) * | 2022-08-15 | 2024-02-15 | Hitachi, Ltd. | Model scaling for multiple environments using minimum system integration |
| CN115563463A (zh) * | 2022-09-13 | 2023-01-03 | 太原理工大学 | 基于深度元学习算法的多工况旋转机械剩余寿命预测方法 |
| US12394185B2 (en) * | 2022-11-28 | 2025-08-19 | Siemens Healthineers Ag | Cross domain segmentation with uncertainty-guided curriculum learning |
| WO2024150861A1 (fr) * | 2023-01-13 | 2024-07-18 | 엘지전자 주식회사 | Dispositif et procédé pour effectuer un apprentissage en ligne d'un modèle d'émetteur-récepteur dans un système de communication sans fil |
| CN115984804B (zh) * | 2023-03-14 | 2023-07-07 | 安徽蔚来智驾科技有限公司 | 一种基于多任务检测模型的检测方法及车辆 |
| CN116561532B (zh) * | 2023-05-31 | 2025-12-12 | 西北工业大学 | 一种航空发动机数字孪生模型的权重自适应训练方法 |
| CN117034091A (zh) * | 2023-09-12 | 2023-11-10 | 国网江苏省电力有限公司宿迁供电分公司 | 一种基于Bi-LSTM-MAML的实时漏电流分类方法 |
| EP4550216A1 (fr) * | 2023-11-03 | 2025-05-07 | Robert Bosch GmbH | Dispositif et procédé d'apprentissage d'un réseau neuronal pour apprentissage multitâche |
| GB2635749A (en) * | 2023-11-24 | 2025-05-28 | Continental Autonomous Mobility Germany GmbH | Computer-implemented method for training a multi-task neural network |
| CN117591048B (zh) * | 2024-01-18 | 2024-04-12 | 中关村科学城城市大脑股份有限公司 | 任务信息处理方法、装置、电子设备和计算机可读介质 |
| US12566744B2 (en) | 2024-01-23 | 2026-03-03 | International Business Machines Corporation | Performing multitask model tuning at edge locations |
| CN117647837B (zh) * | 2024-01-26 | 2024-04-09 | 东北石油大学三亚海洋油气研究院 | 一种地震数据的初至拾取方法、系统及计算机设备 |
| CN118261749B (zh) * | 2024-05-31 | 2024-08-09 | 四川高路文化旅游发展有限责任公司 | 一种基于实时动态模型的桥梁道路预测维护系统及方法 |
| WO2025258846A1 (fr) * | 2024-06-14 | 2025-12-18 | 삼성전자 주식회사 | Procédé de quantification d'un modèle de réseau neuronal à réglage fin pour effectuer de multiples tâches et dispositif pour sa mise en œuvre |
| CN119704143B (zh) * | 2024-10-15 | 2025-11-04 | 大连理工大学 | 一种基于渐进技能课程学习的五指机械灵巧手功能性抓取方法 |
| CN119028138B (zh) * | 2024-10-16 | 2025-01-24 | 清华大学 | 使用元学习的方式来增强交通预测算法的性能的方法 |
| CN119897908B (zh) * | 2025-03-28 | 2025-06-03 | 视瑞(北京)机器人技术有限公司 | 多任务场景下人手动作重定向至异构机器手的方法及装置 |
| CN120031361B (zh) * | 2025-04-24 | 2025-09-09 | 军事科学院系统工程研究院系统总体研究所 | 基于知识驱动的元学习装置的无人机智能调度方法及系统 |
| CN120671763B (zh) * | 2025-06-19 | 2026-03-31 | 深圳市森林鑫科技有限公司 | 硅胶按键导电性强化学习测试系统及方法 |
Family Cites Families (40)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6222525B1 (en) | 1992-03-05 | 2001-04-24 | Brad A. Armstrong | Image controllers with sheet connected sensors |
| US5670988A (en) | 1995-09-05 | 1997-09-23 | Interlink Electronics, Inc. | Trigger operated electronic device |
| US20070081123A1 (en) | 2005-10-07 | 2007-04-12 | Lewis Scott W | Digital eyewear |
| US8696113B2 (en) | 2005-10-07 | 2014-04-15 | Percept Technologies Inc. | Enhanced optical and perceptual digital eyewear |
| US11428937B2 (en) | 2005-10-07 | 2022-08-30 | Percept Technologies | Enhanced optical and perceptual digital eyewear |
| US9304319B2 (en) | 2010-11-18 | 2016-04-05 | Microsoft Technology Licensing, Llc | Automatic focus improvement for augmented reality displays |
| AU2011348122A1 (en) | 2010-12-24 | 2013-07-11 | Magic Leap Inc. | An ergonomic head mounted display device and optical system |
| US10156722B2 (en) | 2010-12-24 | 2018-12-18 | Magic Leap, Inc. | Methods and systems for displaying stereoscopy with a freeform optical system with addressable focus for virtual and augmented reality |
| JP6316186B2 (ja) | 2011-05-06 | 2018-04-25 | マジック リープ， インコーポレイテッドＭａｇｉｃ Ｌｅａｐ，Ｉｎｃ． | 広範囲同時遠隔ディジタル提示世界 |
| EP2760363A4 (fr) | 2011-09-29 | 2015-06-24 | Magic Leap Inc | Gant tactile pour interaction homme-ordinateur |
| US9215293B2 (en) | 2011-10-28 | 2015-12-15 | Magic Leap, Inc. | System and method for augmented and virtual reality |
| WO2013152205A1 (fr) | 2012-04-05 | 2013-10-10 | Augmented Vision Inc. | Dispositifs d'imagerie à grand champ de vision (fov) à capacité de fovéation active |
| US9671566B2 (en) | 2012-06-11 | 2017-06-06 | Magic Leap, Inc. | Planar waveguide apparatus with diffraction element(s) and system employing same |
| KR20150054967A (ko) | 2012-09-11 | 2015-05-20 | 매직 립, 인코포레이티드 | 인체공학적 헤드 마운티드 디스플레이 디바이스 및 광학 시스템 |
| US9202464B1 (en) * | 2012-10-18 | 2015-12-01 | Google Inc. | Curriculum learning for speech recognition |
| US9904889B2 (en) * | 2012-12-05 | 2018-02-27 | Applied Brain Research Inc. | Methods and systems for artificial cognition |
| KR102141992B1 (ko) | 2013-01-15 | 2020-08-06 | 매직 립, 인코포레이티드 | 초고해상도 스캐닝 섬유 디스플레이 |
| IL308285B2 (en) | 2013-03-11 | 2024-11-01 | Magic Leap Inc | System and method for augmentation and virtual reality |
| US9417452B2 (en) | 2013-03-15 | 2016-08-16 | Magic Leap, Inc. | Display system and method |
| US10262462B2 (en) | 2014-04-18 | 2019-04-16 | Magic Leap, Inc. | Systems and methods for augmented and virtual reality |
| US9874749B2 (en) | 2013-11-27 | 2018-01-23 | Magic Leap, Inc. | Virtual and augmented reality systems and methods |
| JP6479785B2 (ja) | 2013-10-16 | 2019-03-06 | マジック リープ， インコーポレイテッドＭａｇｉｃ Ｌｅａｐ，Ｉｎｃ． | 調節可能な瞳孔間距離を有する仮想または拡張現実ヘッドセット |
| US9730643B2 (en) | 2013-10-17 | 2017-08-15 | Siemens Healthcare Gmbh | Method and system for anatomical object detection using marginal space deep neural networks |
| CN107272199B (zh) | 2013-11-27 | 2023-04-07 | 奇跃公司 | 虚拟和增强现实系统与方法 |
| US9857591B2 (en) | 2014-05-30 | 2018-01-02 | Magic Leap, Inc. | Methods and system for creating focal planes in virtual and augmented reality |
| KR102177133B1 (ko) | 2014-01-31 | 2020-11-10 | 매직 립, 인코포레이티드 | 멀티-포컬 디스플레이 시스템 및 방법 |
| CN106233189B (zh) | 2014-01-31 | 2020-06-26 | 奇跃公司 | 多焦点显示系统和方法 |
| US10203762B2 (en) | 2014-03-11 | 2019-02-12 | Magic Leap, Inc. | Methods and systems for creating virtual and augmented reality |
| EP3140780B1 (fr) | 2014-05-09 | 2020-11-04 | Google LLC | Systèmes et procédés de discernement de signaux oculaires et d'identification biométrique continue |
| NZ727350A (en) | 2014-05-30 | 2020-08-28 | Magic Leap Inc | Methods and systems for generating virtual content display with a virtual or augmented reality apparatus |
| US10504040B2 (en) | 2015-06-02 | 2019-12-10 | Nec Corporation | Annealed sparsity via adaptive and dynamic shrinking |
| US9786270B2 (en) * | 2015-07-09 | 2017-10-10 | Google Inc. | Generating acoustic models |
| US9805305B2 (en) | 2015-08-07 | 2017-10-31 | Yahoo Holdings, Inc. | Boosted deep convolutional neural networks (CNNs) |
| US10319374B2 (en) | 2015-11-25 | 2019-06-11 | Baidu USA, LLC | Deployed end-to-end speech recognition |
| WO2017096312A1 (fr) * | 2015-12-04 | 2017-06-08 | Google Inc. | Régularisation de modèles d'apprentissage automatique |
| US11250311B2 (en) * | 2017-03-15 | 2022-02-15 | Salesforce.Com, Inc. | Deep neural network-based decision network |
| US11836611B2 (en) * | 2017-07-25 | 2023-12-05 | University Of Massachusetts | Method for meta-level continual learning |
| IL273991B2 (en) * | 2017-10-26 | 2023-11-01 | Magic Leap Inc | Gradual normalization systems and methods for adaptive loss balancing in deep multitasking networks |
| CA3080005A1 (fr) | 2017-11-14 | 2019-05-23 | Magic Leap, Inc. | Meta-apprentissage pour apprentissage multitache pour reseaux neuronaux |
| US12205348B2 (en) * | 2018-08-02 | 2025-01-21 | Veritone, Inc. | Neural network orchestration |
-
2018
- 2018-11-09 CA CA3080005A patent/CA3080005A1/fr active Pending
- 2018-11-09 AU AU2018368279A patent/AU2018368279A1/en not_active Abandoned
- 2018-11-09 KR KR1020207015255A patent/KR102839893B1/ko active Active
- 2018-11-09 IL IL274424A patent/IL274424B2/en unknown
- 2018-11-09 WO PCT/US2018/060158 patent/WO2019099305A1/fr not_active Ceased
- 2018-11-09 CN CN201880072862.1A patent/CN111328400B/zh active Active
- 2018-11-09 JP JP2020523791A patent/JP7213241B2/ja active Active
- 2018-11-09 US US16/185,582 patent/US11048978B2/en active Active
- 2018-11-09 EP EP18877988.8A patent/EP3710990A4/fr not_active Withdrawn
-
2021
- 2021-06-10 US US17/344,758 patent/US11853894B2/en active Active
Non-Patent Citations (3)
| Title |
|---|
| ALEX GRAVES ET AL: "Automated Curriculum Learning for Neural Networks", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 10 April 2017 (2017-04-10), XP080761985 * |
| CHELSEA FINN ET AL: "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks", 18 July 2017 (2017-07-18), XP055484442, Retrieved from the Internet <URL:https://arxiv.org/pdf/1703.03400.pdf> [retrieved on 20180614] * |
| ZHAO CHEN ET AL: "GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 7 November 2017 (2017-11-07), XP081325645 * |
Also Published As
| Publication number | Publication date |
|---|---|
| JP2021503122A (ja) | 2021-02-04 |
| US20190147298A1 (en) | 2019-05-16 |
| JP7213241B2 (ja) | 2023-01-26 |
| KR102839893B1 (ko) | 2025-07-28 |
| CN111328400B (zh) | 2025-08-19 |
| US11048978B2 (en) | 2021-06-29 |
| KR20200087780A (ko) | 2020-07-21 |
| IL274424B2 (en) | 2024-07-01 |
| EP3710990A1 (fr) | 2020-09-23 |
| WO2019099305A1 (fr) | 2019-05-23 |
| IL274424A (en) | 2020-06-30 |
| CA3080005A1 (fr) | 2019-05-23 |
| IL274424B1 (en) | 2024-03-01 |
| US20210406609A1 (en) | 2021-12-30 |
| CN111328400A (zh) | 2020-06-23 |
| AU2018368279A1 (en) | 2020-05-14 |
| US11853894B2 (en) | 2023-12-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3710990A4 (fr) | Méta-apprentissage pour apprentissage multitâche pour réseaux neuronaux | |
| IL273370A (en) | Photonic neural network system | |
| DK4083789T3 (da) | Specialformålschip til træning af neurale netværk | |
| IL269171A (en) | Machine learning for digital pathology | |
| EP3679522A4 (fr) | Processeur neuronal parallèle pour intelligence artificielle | |
| EP3607504A4 (fr) | Étalement de neurones pour apprentissage profond accéléré | |
| GB201715031D0 (en) | Neural network instruction set architecture | |
| EP3529747A4 (fr) | Réseaux neuronaux pour la modélisation faciale | |
| EP3465550A4 (fr) | Accélérateur pour réseaux neuronaux profonds | |
| EP4418168C0 (fr) | Réseaux neuronaux de transduction de séquence uniquement de décodeur basés sur l'attention | |
| EP3469522A4 (fr) | Accélérateur pour des réseaux neuronaux profonds | |
| EP3446194A4 (fr) | Raccourcis d'application pour carplay | |
| EP3364904A4 (fr) | Balayage variable pour dispositifs d'entrée | |
| MA55328A (fr) | Modulateurs de ror-gamma | |
| EP3630078A4 (fr) | Agents pour chimio-embolisation | |
| DK3490986T3 (da) | Piperidin-cxcr7-receptormodulatorer | |
| EP3492403A4 (fr) | Récipient | |
| EP3615660A4 (fr) | Techniques de microélectrodes pour électroporation | |
| DOS2017000228S (es) | Envase | |
| EP3580223A4 (fr) | Modulateurs du récepteur des strogènes de benzothiophène | |
| EP3597562A4 (fr) | Récipient anti-délaminage | |
| DOS2017000229S (es) | Envase | |
| EP3519028A4 (fr) | Étrier pour harnais | |
| DE112019000481A5 (de) | Variables containersystem | |
| EP3651720C0 (fr) | Système de récipients |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
| PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
| 17P | Request for examination filed |
Effective date: 20200528 |
|
| AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
| AX | Request for extension of the european patent |
Extension state: BA ME |
|
| DAV | Request for validation of the european patent (deleted) | ||
| DAX | Request for extension of the european patent (deleted) | ||
| REG | Reference to a national code |
Ref country code: DE Ref legal event code: R079 Free format text: PREVIOUS MAIN CLASS: G06N0003020000 Ipc: G06N0003040000 |
|
| A4 | Supplementary search report drawn up and despatched |
Effective date: 20210924 |
|
| RIC1 | Information provided on ipc code assigned before grant |
Ipc: G06N 20/00 20190101ALI20210920BHEP Ipc: G06N 3/02 20060101ALI20210920BHEP Ipc: G06N 3/08 20060101ALI20210920BHEP Ipc: G06N 3/04 20060101AFI20210920BHEP |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
| 17Q | First examination report despatched |
Effective date: 20240402 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN |
|
| 18D | Application deemed to be withdrawn |
Effective date: 20251108 |